Explaining Math Word Problem Solvers

Abby Newcomb, Jugal Kalita
7/24/2023
cs.CL

No confident code implementation found for this paper. 3 possible matches can be shown below.

Abstract

Automated math word problem solvers based on neural networks have successfully managed to obtain 70-80\% accuracy in solving arithmetic word problems. However, it has been shown that these solvers may rely on superficial patterns to obtain their equations. In order to determine what information math word problem solvers use to generate solutions, we remove parts of the input and measure the model's performance on the perturbed dataset. Our results show that the model is not sensitive to the removal of many words from the input and can still manage to find a correct answer when given a nonsense question. This indicates that automatic solvers do not follow the semantic logic of math word problems, and may be overfitting to the presence of specific words.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 3 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

ATHENA: Mathematical Reasoning with Thought Expansion

86% match1 repo92023

Techniques to Improve Neural Math Word Problem Solvers

84% match1 repo32023

Learning by Analogy: Diverse Questions Generation in Math Word Problem

83% match1 repo72023

Do Language Models Exhibit the Same Cognitive Biases in Problem Solving as Human Learners?

82% match1 repo52024

Can neural networks do arithmetic? A survey on the elementary numerical skills of state-of-the-art deep learning models

82% match2023

Solving Math Word Problems by Combining Language Models With Symbolic Solvers

82% match1 repo512023

Cite this paper

@article{newcomb2023explaining,
  title  = {Explaining Math Word Problem Solvers},
  author = {Abby Newcomb and Jugal Kalita},
  year   = {2023},
  eprint = {2307.13128},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2307.13128v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2307.13128.svg)](https://codeofpaper.com/paper/2307.13128)

Discussion